כניסההרשמה
חזרה

DevOps - AI Factory

Kaltura
שכר לא צויןIsrael, Bnei Brak, Israel, היברידימידמשרה מלאה
משרה חיצונית, ההגשה באתר החברהאושר שהמשרה פתוחה לפני 11 שעות

You will design and operate distributed AI production systems and infrastructure, including GPU inference, across cloud platforms. You will lead projects from design through production and work with Platform, Development, AI/ML, Architecture, and Product teams.

מה תעשו

  • Lead initiatives from design through implementation and production rollout.
  • Design, build, and operate distributed systems on AWS and GCP.
  • Work across Kubernetes, Docker, Helm, CI/CD, and data, caching, and messaging layers.
  • Modernize and consolidate technology stacks into a single platform.
  • Build and operate infrastructure for AI workloads, including GPU inference.
  • Improve reliability, monitoring, and observability, and troubleshoot issues across system layers.

דרישות

  • 2+ years of experience in DevOps, Platform, or SRE roles operating distributed production systems.
  • 2+ years of experience with cloud inference services and NeoClouds.
  • 2+ years of experience building and maintaining AI Factory systems using KubeFlow, Ray, or similar.
  • 2+ years of experience with GPU inference, such as vLLM, SGLang, or Nvidia Triton.
  • Hands-on expertise with multicloud AWS/GCP/NeoClouds, Terraform or similar, Kubernetes and Helm, Docker, networking, Linux, CI/CD, monitoring, and observability.
  • High proficiency with current AI coding tools.

יתרון

  • Familiarity with AI evaluations and AI observability systems such as Opik, OpenEval, or LangSmith.

תנאי סף

  • 2+ years of experience in DevOps, Platform, or SRE roles
  • 2+ years of experience with cloud inference services and NeoClouds
  • 2+ years of experience building and maintaining AI Factory systems
  • 2+ years of hands-on experience with GPU inference

הטבות

  • Extended private health insurance, including mental health coverage
  • Personal and professional development programs
  • Occasional cross-company long weekends
AWSGCPKubernetesHelmDockerTerraformGPU inferencePrometheus